python获取主域名

from urllib.parse import urlparse

def get_main_domain(url):
    parsed_url = urlparse(url)
    domain = parsed_url.netloc
    if ':' in domain:
        domain = domain.split(':')[0]  # 去除端口号
    return domain

# 示例
url = "https://www.example.com/path/to/page?query=123"
main_domain = get_main_domain(url)
print(main_domain)  # 输出: www.example.com

from urllib.parse import urlparse, urljoin

def get_main_domain_from_relative(relative_url, base_url):
    absolute_url = urljoin(base_url, relative_url)
    return get_main_domain(absolute_url)

# 示例
relative_url = "/path/to/page"
base_url = "https://www.example.com"
main_domain = get_main_domain_from_relative(relative_url, base_url)
print(main_domain)  # 输出: www.example.com